Key Responsibilities: Design, develop, and optimize LLaMA-based and other open-source LLM solutions.Fine-tune models for domain-specific applications using PyTorch, Transformers, or Hugging Face ecosystems.Build and deploy scalable LLM pipelines integrating retrieval-augmented generation (RAG), vector databases, and prompt orchestration tools.Evaluate and benchmark model performance, accuracy, latency, and cost efficiency.Collaborate with data scientists and ML engineers to prepare and clean lar